avnishkr
/

falcon-7b-QueAns

open source llms

fine tuning llms

Model card Files Files and versions Community

Avnish Kumar commited on Jul 6, 2023

Commit

8c8b3a3

·

1 Parent(s): 17544a5

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -19,8 +19,8 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: float16
 The following `bitsandbytes` quantization config was used during training:
-- load_in_8bit: False
-- load_in_4bit: True
 - llm_int8_threshold: 6.0
 - llm_int8_skip_modules: None
 - llm_int8_enable_fp32_cpu_offload: False

 - bnb_4bit_compute_dtype: float16
 The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: True
+- load_in_4bit: False
 - llm_int8_threshold: 6.0
 - llm_int8_skip_modules: None
 - llm_int8_enable_fp32_cpu_offload: False